federated tensorflow error
I got "OverflowError: cannot convert float infinity to integer" when i call evaluate(server_state) on Federated Tensorflow
/opt/conda/lib/python3.10/site-packages/keras/utils/generic_utils.py:238: RuntimeWarning: divide by zero encountered in log10
numdigits = int(np.log10(self.target)) + 1
---------------------------------------------------------------------------
`OverflowError Traceback (most recent call last)
Cell In[173], line 1
----> 1 evaluate(server_state)
Cell In[171], line 8, in evaluate(server_state)
3 keras_model.compile(
4 loss=tf.keras.losses.SparseCategoricalCrossentropy(),
5 metrics=[tf.keras.metrics.SparseCategoricalAccuracy()]
6 )
7 keras_model.set_weights(server_state)
----> 8 keras_model.evaluate(central_test_data)
File /opt/conda/lib/python3.10/site-packages/keras/utils/traceback_utils.py:70, in filter_traceback.<locals>.error_handler(*args, **kwargs)
67 filtered_tb = _process_traceback_frames(e.__traceback__)
68 # To get the full stack trace, call:
69 # `tf.debugging.disable_traceback_filtering()`
---> 70 raise e.with_traceback(filtered_tb) from None
71 finally:
72 del filtered_tb
File /opt/conda/lib/python3.10/site-packages/keras/utils/generic_utils.py:238, in Progbar.update(self, current, values, finalize)
235 message += "\n"
237 if self.target is not None:
--> 238 numdigits = int(np.log10(self.target)) + 1
239 bar = ("%" + str(numdigits) + "d/%d [") % (current, self.target)
240 prog = float(current) / self.target`
OverflowError: cannot convert float infinity to integer
